INDEX

Explanations

I feel or experienced states

This neuron detects first-person self-references (pronouns like I, my, we, our, I’ve, etc.).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 your

-1.27

you

-1.18

^{\

-1.14

_))

-1.10

 mengganggu

-1.09

 ($('#

-1.05

 mengerti

-0.98

 современных

-0.96

延伸閱讀

-0.96

 debes

-0.95

POSITIVE LOGITS

 felt

1.27

 відчу

1.23

 feel

1.21

 feels

1.15

覺得

1.10

sikt

1.08

 feeling

1.06

Ễ

1.05

 považ

1.05

𝓥

1.04

Activations Density 0.052%